Papers › Discrete Latent Variable Representations for Low-Resource Text Classification

Discrete Latent Variable Representations for Low-Resource Text Classification

11 Jun 2020ACL 2020 6arXiv:2006.06226archive 2025-07-28

Shuning Jin, Sam Wiseman, Karl Stratos, Karen Livescu

While much work on deep latent variable models of text uses continuous latent variables, discrete latent variables are interesting because they are more interpretable and typically more space efficient. We consider several approaches to learning discrete latent variable models for text in the case where exact marginalization over these variables is intractable. We compare the performance of the learned representations as features for low-resource document and sentence classification. Our best models outperform the previous best reported results with continuous representations in these low-resource settings, while learning significantly more compressed representations. Interestingly, we find that an amortized variant of Hard EM performs particularly well in the lowest-resource regimes.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

shuningjin/discrete-text-rep officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

ClassificationGeneral ClassificationSentenceSentence ClassificationText Classificationtext-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections